Artificial neural networks/reinforcement learning
Weekly outline
-
Reinforcement Learning for Bandit problems
-
Bellman Equation and SARSA
-
Markov Decision Processes and Convergence of SARSA
-
Variants of TD-learning methods and eligibility traces
-
TD-learning and function approximation
-
Policy-gradient methods
-
-
From Policy Gradient to Actor-Critic
-
Model-Free Deep Reinforcement Learning
-
Model-Based Deep Reinforcement Learning
-
Reinforcement Learning and the Brain
-
From brain-style computing to neuromorphic computing
-
Surprise and Novelty in Reinforcement Learning
-
Exam Q&A